用远程交通数据估算伦敦本地空气污染物，多场景机器学习对比，城市监测缺口下的实用解法。
arXiv:2608.23219v1 Announce Type: new Abstract: Vehicular traffic is a major source of air pollution; however, the contribution of remotely acquired t…
小孩学语言只需少量样本，大模型却要吞下整座城市几代人的语料，这个谜题正动摇AI的底层逻辑。
People have been talking to each other for at least 100,000 years, as best we can tell. And in all that time, there has been only one thing in the wor…
从分解到传递，这项研究让LLM智能体把技能迁移到新任务，少训练、更高效，跨任务学习的进阶思路。
arXiv:2608.20274v1 Announce Type: cross Abstract: Large language model (LLM) agents can induce skills from completed tasks and reuse them later to gro…
为Pandas DataFrame注入AI能力，自动完成数据增强与特征工程，数据预处理从此更高效。
Article URL: https://github.com/mljar/enrichment Comments URL: https://news.ycombinator.com/item?id=49372451 Points: 1 # Comments: 0
用智能体自动合成特征提取器，破解算法选择难题，AI研究新思路。
arXiv:2608.17170v1 Announce Type: new Abstract: Algorithm selection for constraint satisfaction problems requires extracting features that capture pro…
拆解Adam优化器背后的脆弱根基，用原理推导新设计，深度学习调参必备的理论参考。
arXiv:2608.16760v1 Announce Type: new Abstract: Reliable optimization is central to neural network (NN) training, yet Adam, the default optimizer for …
AI落地建筑运营的软件工程指南，涵盖系统设计到部署的完整链路。
arXiv:2608.16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems prom…
面向ML研究与科学发现的超长时程智能体，自主推演实验闭环，值得AI从业者关注。
arXiv:2608.14354v1 Announce Type: new Abstract: Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons is…
多智能体协作面临延迟挑战？这篇论文教你用学习驱动编排，显著提升系统响应效率。
arXiv:2601.10560v2 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) coordinate multiple LLM-powered agents through structured workflow…
把AI管道设计成决策就绪的ITSM智能，IT运维智能化必读方案。
arXiv:2608.12670v1 Announce Type: cross Abstract: IT service management (ITSM) systems accumulate large volumes of heterogeneous ticket data that are …
受限Logit模型如何在大规模场景精准估算需求转移系数，为零售决策提供关键依据。
arXiv:2608.12680v1 Announce Type: new Abstract: Item demand forecasting is an integral component of store assortment optimization. Existing literature…
另辟蹊径——不调LLM，训练harness也能让跨模型、跨基准全面涨点，值得一试。
Article URL: https://github.com/workofart/harness-training Comments URL: https://news.ycombinator.com/item?id=49293267 Points: 4 # Comments: 0
横跨多领域梳理可解释NLP研究全景，257篇参考文献与15张表格堪称实用地图。
arXiv:2502.00837v3 Announce Type: replace-cross Abstract: Natural Language Processing (NLP) is now embedded in critical sectors including healthcare, …
面向梯度提升决策树的细粒度量化与硬件生成方案，高效兼顾精度与硬件效率，ASAP'26收录，值得关注。
arXiv:2608.12140v1 Announce Type: cross Abstract: Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardwa…
盘点大模型参与重大数学突破的真实案例，看AI如何助力数学研究前沿。
Article URL: https://mathoverflow.net/questions/502120/examples-for-the-use-of-ai-and-especially-llms-in-major-mathematical-development Comments URL: …
用生成模型加速蒙特卡洛采样，解锁复杂概率分布推断的新思路，值得关注。
arXiv:2608.07648v1 Announce Type: cross Abstract: Sampling high-dimensional probability distributions is a central task in scientific computing, with …
探索将重复性LLM调用替换为regex、解析器等传统管道，降低成本和延迟，值得关注。
We are investigating whether recurring LLM workloads can be replaced, where appropriate, by automatically constructed pipelines of regexes, determinis…
跳出循环的隐式监督，多保真贝叶斯优化迎来新范式，降本增效直击采样痛点。
arXiv:2608.04113v1 Announce Type: cross Abstract: Black-box optimization is a ubiquitous problem in science and engineering, often dealing with expens…
用机器学习剖析量子热力学熵，单粒子量子引擎的洞察新视角，交叉前沿值得一读。
arXiv:2305.06177v1 Announce Type: cross Abstract: We present a thermodynamic analysis of a quantum engine that uses a single quantum particle as its w…
一份用信赖域框架重新审视自适应矩估计的数学研究，适合想深挖优化器收敛原理的读者。
arXiv:2608.04026v1 Announce Type: cross Abstract: In this paper, we develop a trust-region framework for understanding the behavior of adaptive moment…